Zili Wang

Lyapunov Neural Network with Region of Attraction Search

2024

Deep learning methods have been widely used in robotic applications, making learning-enabled control design for complex nonlinear systems a promising direction. Although deep reinforcement learning methods have demonstrated impressive empirical performance, they lack the stability …

MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework

2023 · arXiv (Cornell University)

Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs). Existing LLM-based multi-agent systems can already solve simple dialogue tasks. Solutions to more complex tasks, however, …